小波神经网络用于非线性函数逼近的研究

神经网络具有良好的学习特性,而小波变换具有良好的时频局部化特性,将二者结合在一起构成小波神经网络,网络隐层采用morlet小波函数,输出层采用线性函数,可使该网络兼具神经网络和小波变换的优点.作者分别用小波网络和BP网络逼近一非线性函数,其结果表明,在相同的误差条件下,小波网络的收敛速度要远远快于一般的BP网络.

Wavelet neural networks in the research of approximating nonlinear functions

Neural network has good learning characteristics,and wavelet transform has good localization characteristics both in time?domain and frequency?domain.The wavelet neural network can be abtained by combining them.The morlet wavelet function and linear function are employed as an activation function in the hidden and output layer respectively.So the wavelet neural networks have better characteristics comparing with wavelet transform and neural network.The contrast of the wavelet neural network and BP network in approximating nonlinear function shows that the rate of convergence of the wavelet neural network is faster than the speed of BP network in the same errors.